AI Data Engineer: Production AI, LLM & RAG Pipelines

AVEVA Asia Pacific Sdn Bhd; Kuala Lumpur; Hybrid; MYR 180,000 - 260,000; Full time

Job summary

AVEVA Asia Pacific Sdn Bhd in Kuala Lumpur seeks a Data / AI Engineer to help deliver AI‑first features by designing and implementing production‑ready capabilities across global platforms. You will work with Azure OpenAI, Tongyi Qianwen, and MCP‑based agent workflows to support onboarding, data intake, and SaaS augmentation.

The role requires 5–8 years in software/data engineering with at least 2 years in AI/ML production, strong Python, and experience with vector databases and ETL/ELT

Qualifications

• 5–8 years of software or data engineering experience, with 2+ years focused on AI/ML in production.
• Experience with cloud AI services and API development using modern frameworks.
• Strong Python experience for data and AI workloads.
• Knowledge of vector databases and embedding models.

Responsibilities

• Design and implement AI‑powered features for the Unified Partner Experience, including assisted intake and onboarding automation.
• Build integrations with Azure OpenAI and Alibaba Tongyi Qianwen / PAI for global and regional AI capabilities.
• Develop MCP agents, tool integrations, and RAG pipelines to support SaaS augmentation workflows.
• Build data pipelines for extraction, transformation, embedding generation, and vector storage.
• Implement prompt engineering, evaluation frameworks, safety guardrails, and monitoring for production AI services.

Skills

Python

Azure OpenAI Service

OpenAI APIs

RAG pipelines

LLM‑powered apps

Data engineering

ETL/ELT pipelines

English communication

Tools

LangChain

Semantic Kernel

MCP

Job description

AVEVA Asia Pacific Sdn Bhd in Kuala Lumpur seeks a Data / AI Engineer to help deliver AI‑first features by designing and implementing production‑ready capabilities across global platforms. You will work with Azure OpenAI, Tongyi Qianwen, and MCP‑based agent workflows to support onboarding, data intake, and SaaS augmentation.

The role requires 5–8 years in software/data engineering with at least 2 years in AI/ML production, strong Python, and experience with vector databases and ETL/ELT